Synthetic Control Methods for Proportions

Synthetic control methods are extensively utilized in political science for estimating counterfactual outcomes in case studies and difference-in-differences settings, often applied to model counterfactual proportional data. However, the conventional synthetic control methods are designed for univariate outcomes, leading researchers to model counterfactuals for each proportion separately. This paper introduces an extension, proposing a method to simultaneously handle multivariate proportional outcomes. Our approach establishes constant control comparisons by using the same weights for each proportion, improving comparability while adhering to treatment constraints. Results from a simulation study and the application of our method to data from a recently published article on campaign effects in the 2019 Spanish general election underscore the benefits of accounting for the interplay of proportional outcomes. This advancement extends the validity and reliability of synthetic control estimates to common outcomes in political science.